Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.4048. Min Act: -0.0001

Data Index: 1326498 (C4 (Web Text))

Max Activating Token Index: 166

Text #1

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.2760. Min Act: -0.0000

Data Index: 474184 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.2201. Min Act: -0.0001

Data Index: 1085496 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.1572. Min Act: -0.0000

Data Index: 630633 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.1496. Min Act: -0.0000

Data Index: 1161464 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.1309. Min Act: -0.0000

Data Index: 680010 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.1039. Min Act: -0.0000

Data Index: 1029010 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9742. Min Act: -0.0001

Data Index: 1065635 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.1789. Min Act: -0.0001

Data Index: 1313989 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9486. Min Act: -0.0000

Data Index: 403081 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9270. Min Act: -0.0000

Data Index: 78941 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.1388. Min Act: -0.0000

Data Index: 364680 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9275. Min Act: -0.0000

Data Index: 632190 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 2.4048. Min Range: -2.4048

Max Act: 2.0179. Min Act: -0.0000

Data Index: 115681 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9168. Min Act: -0.0001

Data Index: 967826 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9854. Min Act: -0.0001

Data Index: 651822 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9662. Min Act: -0.0001

Data Index: 1223706 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9629. Min Act: -0.0000

Data Index: 18920 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.9328. Min Act: -0.0000

Data Index: 1106488 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 2.4048. Min Range: -2.4048

Max Act: 1.7170. Min Act: -0.0000

Data Index: 1095979 (C4 (Web Text))

Max Activating Token Index: 645